一句话：提出基于生成式 AI 的 LikeThis!，让用户用截图和评论生成多个 UI 改进方案，提升反馈可理解性与可执行性。
用户反馈对移动应用演进至关重要，但用户常提交模糊甚至破坏性的反馈。LikeThis! 是一个生成式 AI 方法，旨在赋能用户提交更具建设性的 UI 反馈：输入用户评论与截图，即可生成多个改进备选方案供用户选择；生成设计前先产出解决方案规约是关键步骤。评估先在公开 UI 设计批评数据集上基准测试，GPT-Image-1 在解决 UI 问题、保持保真且不引入新问题方面显著优于其他三种先进图像生成模型。随后在 10 个生产应用中，15 名用户用其提交反馈，开发者评估可理解性与可执行性。结果表明，生成改进能从用户和开发者视角提升反馈质量，为 AI 辅助协作铺路。
User feedback is crucial for the evolution of mobile apps. However, research suggests that users tend to submit uninformative, vague, or destructive feedback. Unlike recent AI4SE approaches that focus on generating code and other development artifacts, our work aims at empowering users to submit better and more constructive UI feedback with concrete suggestions on how to improve the app. We propose LikeThis!, a GenAI-based approach that takes a user comment with the corresponding screenshot to immediately generate multiple improvement alternatives, from which the user can easily choose their preferred option. To evaluate LikeThis!, we first conducted a model benchmarking study based on a public dataset of carefully critiqued UI designs. The results show that GPT-Image-1 significantly outperformed three other state-of-the-art image generation models in improving the designs to address UI issues while keeping the fidelity and without introducing new issues. An intermediate step in LikeThis! to generate a solution specification before changing the design was key to achieving effective improvement. Second, we conducted a user study with 10 production apps, where 15 users used LikeThis! to submit their feedback on encountered issues. Later, the developers of the apps assessed the understandability and actionability of the feedback with and without generated improvements. The results show that our approach helps generate better feedback from both user and developer perspectives, paving the way for AI-assisted user-developer collaboration.
@inproceedings{abs-2603-04245,
title = {LikeThis! Empowering App Users to Submit UI Improvement Suggestions Instead of Complaints},
author = {Jialiang Wei and Ali Ebrahimi Pourasad and Walid Maalej},
booktitle = {ICSE},
year = {2026},
doi = {10.1145/3744916.3787834}
}